Month: April 2018

  • Build Android project with multi flavour on Jitpack

    Lately my team has built an Android project that needs to run on multiple channels and platform: Google, Amazon, mobile, tablet and TV. It took us sometime to plan to enable us working in parallel within tight Sprint schedule. At the end we designed a structure that includes a core module which is shared on […]

  • TensorFlow Image Recognition: train your own model

    TensorFlow is a powerful tool, and its image recognition model contains millions of parameters. To train a model from scratch, you will need a lot of data, but if you want to create a project, which recognizes an image with the labeling of “Molly-the dog”, rather than just “a dog”, or “Isabella wedding” rather than […]

  • TensorFlow Lite Image recognition: Android with Kotlin

    TensorFlow is a wonderful tool for machine learning, where its main purpose is designed for neural network models. When it comes to mobile, Google has provided us with two libraries: TensorFlow mobile and TensorFlow Lite. They both works on Android and iOS. While TensorFlow mobile is recommended to use for developers who have a pre-trained model (a trained model is like […]